Principal Data Scientist

Summary

Join RefinedScience as a Principal Data Scientist and contribute to advancing healthcare through data-driven insights. This remote position, based anywhere in the continental US with occasional travel to Aurora, CO, requires expertise in machine learning, statistical analysis, and big data technologies. You will lead projects, mentor junior scientists, and collaborate with cross-functional teams. The ideal candidate possesses a strong background in data science and a proven ability to solve complex problems. RefinedScience offers a competitive salary, comprehensive benefits, and a collaborative work environment.

Requirements

• Possess a B.Sc. with 5+ years of working experience, or MSc / PhD with 1+ year postgraduate experience in data science, mathematics, statistics, biostatistics, computer science or related quantitative discipline
• Have superb written and verbal communication skills
• Demonstrate evidence of learning and scientific problem-solving skills
• Have thorough working knowledge of R/Quarto/Python and SQL
• Have experience in software (e.g., package) development for reproducibility
• Have experience in at-least one web application (R Shiny/JAVA/Tableau)
• Have applied knowledge of working in Linux, AWS, GCP, and GitHub
• Have thorough theoretical and applied understanding on at least three or more areas such as multistate survival analyses, mixed modeling, non-parametric modeling, longitudinal/time series modeling, meta-analysis/evidence synthesis, machine learning models (e.g., gradient boost, ensemble models, SVM, neural net, transformers, and their counterparts), distributed algorithms, federated algorithms, adversarial models, and Bayesian models
• Have experience working in a collaborative environment being as a team player
• Be willing to travel to RefinedScience location (Denver, CO) approximately once per month and travel up to 15%

Responsibilities

• Implement cutting edge statistical and machine learning methods to develop empirical models
• Develop statistical learning-based models
• Develop inferential/causal models
• Develop machine learning based predictive-and-interpretive models
• Develop federated/distributed learning models
• Implement advanced artificial intelligence (AI) tools such as large language models to boost efficiency of data extraction and curation
• Process, manage, manipulate, and visualize large clinical data adhering to best practices
• Generate real world evidence and clinical insights while validating model performances
• Understand complex clinical problems and solve them (empirically and intuitively)
• Collaborate with academicians, clinicians, data managers, data engineers, data analysts, bioinformaticians, non-technical partners, business personnel, and other stakeholders
• Contribute to preparing scientific manuscripts

Preferred Qualifications

• Have a proven track record of publication in major scientific journals, conferences or scientific proceedings
• Have experience working with electronic health records (EHR) data
• Have experience in designing clinical trials (single-arm, synthetic, or randomized)
• Have experience working in early-stage Biotech environment

Benefits

• Medical, Dental and Vision insurance
• Life, AD&D, Short-term and Long-term Disability Insurance (none is 100% covered)
• HSA Spending Accounts
• 22 Vacation days
• 10 Paid Holidays and Sick Time (120 hours per year)
• 401(K) Plan
• Remote work